Cellular Access Point Classification for Network Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing cellular network management systems face challenges in efficiently managing access points using AI-based solutions, particularly in identifying and addressing performance variations among access points.
Innovation Solution
A method utilizing a machine learning model to classify access points based on performance metrics, identify access points requiring corrective actions, and enable automatic configuration adjustments to optimize network performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AI-based solutions are implemented to manage access points, then network optimization capability is improved, but system complexity increases
Solution Approach 1:
The patent segments access points into different classes based on their performance metrics and characteristics. This segmentation allows the system to apply different management strategies to different AP types, reducing overall system complexity while maintaining sophisticated optimization capabilities. The machine learning model processes data in structured segments rather than handling all APs uniformly.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between raw network data and management decisions. This intermediary layer processes and interprets complex network behavior patterns, transforming raw data into actionable insights without requiring direct complex interactions between all system components, thus managing system complexity.
2Measurement precision
If access points are classified into multiple classes, then management precision is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary classification of access points into different classes during network setup or periodic reclassification. Once classified, access points can be managed using pre-determined strategies for each class, reducing real-time processing requirements. The machine learning model can be pre-trained on historical data to make rapid classification decisions.
Solution Approach 2:
The patent applies classification and sophisticated management strategies selectively to access points that require it, rather than uniformly applying complex management to all APs. This partial action approach maintains high management precision for critical APs while reducing overall processing time by skipping detailed analysis for less critical ones.
3Productivity
If corrective actions are applied to improve performance, then network efficiency is improved, but operational complexity increases
Solution Approach 1:
The patent implements self-service mechanisms where the machine learning model automatically identifies performance issues and applies corrective actions without requiring manual intervention. The system monitors its own performance metrics, detects anomalies, and autonomously adjusts parameters to optimize network efficiency, reducing operational complexity by eliminating the need for manual analysis and decision-making.
Solution Approach 2:
The patent establishes feedback loops where performance metrics are continuously monitored, compared against target values, and used to automatically adjust access point configurations. This closed-loop feedback system enables continuous optimization of network efficiency while managing operational complexity through automated, rule-based corrective actions rather than manual processes.
Data Source
AI summary
There are provided a method and system to control traffic in a cellular network comprising a plurality of access points (APs) serving a plurality of user equipment devices (UEs). The method comprises: using a machine learning (ML) model to classify at least part of the APs in accordance with a first part of AP metrics thereof, thereby giving rise to a plurality of classes, each comprising peering APs; for a given class, processing AP performance metrics of peering APs classified to the given class to identify, among them, one or more first APs with negative performance variations above a variation threshold and, thereby, requiring corrective actions; and enabling one or more corrective actions with regard to the identified one or more first APs.